Alternatives
Products that do what Toolkit for LLM Fine-Tuning, Ablating and Testing does
Hello all! Very happy to share this toolkit that allows you to fine-tune your choice of open-source LLMs on your data! The toolkit also allows you to run ablation studies across LLMs, prompt designs, training configurations, and can ingest different data files -- all through just ONE YAML file! After fine-tuning, you can also run a bunch of tests to ensure that the fine-tuned LLM behaves as expected, enabling faster time-to-production! Why this toolkit? Why now? While closed-source LLMs have become popular for chat-based applications, enterprises are considering a shift to self-hosted SLMs…
- 1
LLM reinforcement fine-tuning platform to improve LLM output
2025
- 2
- 3FT
Aug 2026 · github.com
- 4
- 5
- 6
- 7
- 8RL
We've been building data pipelines that scrape websites and extract structured data for a while now. If you've done this, you know the drill: you write CSS selectors, the site changes its layout, everything breaks at 2am, and you spend your morning rewriting parsers. LLMs seemed like the obvious fix — just throw the HTML at GPT and ask for JSON. Except in practice, it's more painful than that: - Raw HTML is full of nav bars, footers, and tracking junk that eats your token budget. A typical product page is 80% noise. - LLMs return malformed JSON more often than you'd expect, especially with…
Mar 2026 · github.com
- 9CD
Hey HN, this is David from Aluna (YC S24). We work with diagnostic labs to build datasets and evals for oncology tasks. I wanted to share a simple RL environment I built that gave frontier LLMs a set of tools that lets it zoom and pan across a digitized pathology slide to find the relevant regions to make a diagnosis. Here are some videos of the LLM performing diagnosis on a few slides: (https://www.youtube.com/watch?v=k7ixTWswT5c): traces of an LLM choosing different regions to view before making a diagnosis on a case of small-cell carcinoma of the lung…
Nov 2025
- 10TS
Hi everyone, I just released an open source load testing tool for LLMs: https://github.com/twerkmeister/tokenflood === What is it and what problems does it solve? === Tokenflood is a load testing tool for instruction-tuned LLMs hat can simulate arbitrary LLM loads in terms of prompt, prefix, and output lengths and requests per second. Instead of first collecting prompt data for different load types, you can configure the desired parameters for your load test and you are good to go. It also let's you assess the latency effects of potential prompt parameter changes before…
Nov 2025 · github.com
- 11IB
I was overspending on GPT-4o. It was really hard to compare different models I could switch to, so I built this LLM comparison tool. It shows leaderboards, pricing, and performance data across 100+ LLMs (including all major providers and open-source models). Key features: - Live pricing comparisons - Benchmark Scores (MMLU, HumanEval, GPQA, etc.) - Context length vs cost analysis - Speed/throughput tests across providers - Quality vs price visualizations - Open source (all data verifiable) Try it out: https://llmstats.com I'd like to know your opinion :) Tech stack: Next.js,…
2025 · llm-stats.com
- 12MS
Hey HN, I’m the author. I built Misata because existing tools (Faker, Mimesis) are great for random rows but terrible for relational or temporal integrity. I needed to generate data for a dashboard where "Timesheets" must happen after "Project Start Date," and I wanted to define these rules via natural language. How it works: LLM Layer: Uses Groq/Llama-3.3 to parse a "story" into a JSON schema constraint config. Simulation Layer: Uses Vectorized NumPy (no loops) to generate data. It builds a DAG of tables to ensure parent rows exist before child rows (referential integrity).…
Dec 2025 · github.com
- 13IB
Built a simple web app that tells you which open-source LLMs will work on your hardware. It auto-detects your specs, shows compatible models from Hugging Face, gives realistic performance estimates (tokens/sec), and recommends quantization settings. You can also manually input specs to see "what if I upgraded my RAM?" Made this after wasting time downloading giant models only to find they crawled on my hardware. Hope it saves you some frustration!
2025 · caniusellm.com
- 14KL
LLM agents often place raw JSON tool outputs directly in the prompt. After a few tool calls, earlier results get compacted or truncated and answers become incorrect or inconsistent. I built Sift, a drop-in MCP gateway that stores tool outputs as local artifacts (filesystem blobs indexed in SQLite) and returns an `artifact_id` plus compact schema hints when responses are large or paginated. Instead of reasoning over full JSON in the prompt, the model runs a small Python query: def run(data, schema, params): return max(data, key=lambda x: x["magnitude"])["place"] Query code runs in a…
Mar 2026 · github.com
- 15EL
Hey HN! I built Experiment to solve a common frustration in LLM development: the lack of proper tools for prompt engineering experimentation. Here's what makes it different: Key Features: - Load and edit chat completion logs from CSV files - Fork and modify specific conversation entries - Run inference via Anthropic, Mistral, and OpenAI - Define custom tools using JSONSchema format - Visual tool usage analysis with collapsible, sorted key-value pairs - Full mobile support and available as installable PWA Technical Highlights: - Built with React using custom isomorphic architecture -…
2025 · github.com
- 16AL
Try it out here: https://labs.refuel.ai/playground Refuel LLM (84.2%) outperforms trained human annotators (80.4%), GPT-3-5-turbo (81.3%), PaLM-2 (82.3%) and Claude (79.3%) across a benchmark of 15 text labeling datasets. It is a Llama-v2-13b base model, trained on over 2500 unique datasets (5.24B tokens) spanning categories such as classification, entity resolution, matching, reading comprehension and information extraction.
2023
- 17NL
Refuel LLM (84.2%) outperforms trained human annotators (80.4%), GPT-3-5-turbo (81.3%), PaLM-2 (82.3%) and Claude (79.3%) across a benchmark of 15 text labeling datasets. It is a Llama-v2-13b base model, trained on over 2500 unique datasets (5.24B tokens) spanning categories such as classification, entity resolution, matching, reading comprehension and information extraction. Here is the interactive demo: https://labs.refuel.ai/playground. Pretty fun to play with!
2023
- 18RA
We built RapidFire AI, an open-source Python tool to speed up LLM fine-tuning and post-training with a powerful level of control not found in most tools: Stop, resume, clone-modify and warm-start configs on the fly—so you can branch experiments while they’re running instead of starting from scratch or running one after another. - Works within your OSS stack: PyTorch, HuggingFace TRL/PEFT), MLflow. - Hyperparallel search: launch as many configs as you want together, even on a single GPU - Dynamic real-time control: stop laggards, resume them later to revisit, branch promising configs in…
Sep 2025 · github.com
- 19AO
Hi, We are building an open-source framework for loading and structuring LLM context to create accurate and explainable LLM answers using knowledge graphs and vector stores. We built the tool with four main concepts in mind: 1. Loader -> uses dlt in the backend to load and structure the data 2. Cognify step -> creates a graph with summaries, labels and factoids that are interconnected across the documents and stored as a representation in the vector store 3. Optimizer -> Uses DSPy to optimize LLM queries, and we plan to extend it to most of the knobs we can turn, like chunking etc. 4. Search…
2024 · github.com
- 20IM
Live demo here: http://fonctionlabs.com:8000 Similarly to aka_sh (guess we were working parallelly on similar topics), I created with my brother a chainlit-based webapp, which summarizes Youtube videos in order to gain time. It works as an RAG-based LLM, and is very light in the sense that it does not use RAG libraries like langchain or llamaindex. You can use it with your own OpenAI API key. It also supports local models like Mistral, or Llamma. It is ofc open-source, and you can deploy with Docker if you choose. Some of the next steps are: - using whisper to be able to compute a…
2024 · github.com
- 21IB
Hey HN, I've been working on something cool that I wanted to share with you all. It's called Viewpoint, an analytics tool for LLMs like OpenAI, Anthropic models, and Gemini. The idea came from the constant flood of new LLM models and the need to figure out which ones work best for my projects without breaking the bank. With viewpoint, I can track token usage, costs, latency(WIP), and traffic over time, making it easier to compare different models and see which ones perform best and save money. The tool works asynchronously, so it doesn't add any latency to your LLM requests, and you have…
2024 · viewpointhq.com
- 22EA
A few months ago I was working on a flight search engine that would include pet transport costs (I know a few by hearth but storing them and make the calculations in the UI would be nice) While I was collecting pet pricing from several airlines I strugled to extract data in a common format without hallucinated values. That's when I thought: What if I use multiple LLMs and take the most common response to improve accuracy? This idea became this new project. You provide your documents, an SQLModel schema, an LLM provider, plus what you'd like to extract and Extrai does the rest. Including…
Nov 2025 · github.com
- 23UA
Hey HN! After using a combination of Unsloth and Axolotl a lot, and finding it generally painful to figure out the right performance tuning for things like batch sizing and multi-GPU sharding, I wrote a small Python lib that sets up known-good LoRA training configurations for Llama 3.1 8B and 70B Instruct, and includes helpers for distilling from larger models or training on serverless finetuning platforms, and includes a walkthrough for distilling DeepSeek-R1 into a Llama 3.1 8B LoRA... But you can use it for pretty much any finetuning task, not just distilling large models!
2025 · github.com
- 24HF
We have a massive GPU cluster and developed our own infrastructure to manage the cluster and train massive models. There's how it works: 1. You upload the dataset with preconfigured format into HuggingFaсe [1]. 2. Choose your LLM (e.g. LLaMa 70B, Mistral 7B) 3. Place your submission into the queue 4. Wait for it to get trained. 5. Then you get your trained model there on HuggingFace. Essentially, why would we want to do it? 1. We already have an experience with training big LLMs. 2. We could achieve near-perfect infrastructure performance for training. 3. Sometimes GPUs have just nothing to…
2023 · higgsfield.xyz
Ranked by how close each launch is in meaning, then by votes. Refine with a description →